© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 14119
    Prev
    Next
    INDEX
    Explanations

    biomedical terms and phrases related to medical conditions and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by archaic or uncommon suffixes

    np_acts-logits-general · gemini-2.0-flash

    adamantane derivatives, intestine-specific, autonomic tone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     p
    -0.64
    URUS
    -0.63
    ADVERTISEMENT
    -0.60
    Joke
    -0.58
     "
    -0.57
    IZON
    -0.54
     
    -0.53
     J
    -0.52
     I
    -0.51
     ро
    -0.50
    POSITIVE LOGITS
     Efq
    1.30
     himſelf
    1.29
     becauſe
    1.27
     myſelf
    1.23
     themſelves
    1.23
     ſy
    1.21
     itſelf
    1.21
     whoſe
    1.17
     ſeveral
    1.16
     Reſ
    1.15
    Activations Density 1.562%

    No Known Activations